Check training budget status and resolve over-budget tasks by choosing to resume or terminate after human review.
训练预算控制——查预算状态 / 超预算人审续跑或终止。
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | 操作：status 查预算 / resolve 人审续跑或终止 | |
| job_id | Yes | 训练任务标识（job.json 的 jobId） | |
| decision | No | resolve 时的人审决策：resume 续跑 / terminate 终止 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It mentions that the tool can resume or terminate a training run, implying mutation, but it does not explain side effects, irreversibility, permissions, or consequences of terminating a job. This is a meaningful gap for a potentially destructive action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with a clear dash-separated structure that fronts the two primary operations. It contains no filler or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that can terminate a training job)Skip, the description is incomplete: it does not say what status returns, whether the decision is persisted, or that decision is effectively required when action=resolve. With no output schema and no annotations, an agent needs more behavioral and conditional guidance to invoke this correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents action, job_id, and decision meaningfully. The description adds minimal semantic value beyond the schema, mainly restating the action and decision concepts. A baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the resource (training budget) and the specific operations: querying budget status and performing a human-review resolution to resume or terminate an over-budget job. This distinguishes it from generic sibling tools like train_status, though it does not explicitly name any alternative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives concrete usage context: use it to check budget status or to make a human-review decision (resume/terminate) when over budget. It does not explicitly contrast with sibling tools such as train_status or hitl_resolve, but the intended scenarios are clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.